add common base class, BaseStringArray

Author: simonjayhawkins

pandas/core/arrays/string_.py

@@ -43,6 +43,7 @@
     IntegerArray,
     PandasArray,
 )
+from pandas.core.arrays.base import ExtensionArray
 from pandas.core.arrays.floating import FloatingDtype
 from pandas.core.arrays.integer import _IntegerDtype
 from pandas.core.construction import extract_array
@@ -52,8 +53,6 @@
 if TYPE_CHECKING:
     import pyarrow
 
-    from pandas.core.arrays.string_arrow import ArrowStringArray
-
 
 @register_extension_dtype
 class StringDtype(ExtensionDtype):
@@ -172,7 +171,7 @@ def __hash__(self) -> int:
     # "ExtensionDtype"
     def construct_array_type(  # type: ignore[override]
         self,
-    ) -> type_t[StringArray | ArrowStringArray]:
+    ) -> type_t[BaseStringArray]:
         """
         Return the array type associated with this dtype.
 
@@ -195,7 +194,7 @@ def __str__(self):
 
     def __from_arrow__(
         self, array: pyarrow.Array | pyarrow.ChunkedArray
-    ) -> StringArray | ArrowStringArray:
+    ) -> BaseStringArray:
         """
         Construct StringArray from pyarrow Array/ChunkedArray.
         """
@@ -225,7 +224,11 @@ def __from_arrow__(
             return StringArray(np.array([], dtype="object"))
 
 
-class StringArray(PandasArray):
+class BaseStringArray(ExtensionArray):
+    pass
+
+
+class StringArray(BaseStringArray, PandasArray):
     """
     Extension array for string data.
 

pandas/core/arrays/string_arrow.py

@@ -47,7 +47,10 @@
 from pandas.core.arrays.boolean import BooleanDtype
 from pandas.core.arrays.integer import Int64Dtype
 from pandas.core.arrays.numeric import NumericDtype
-from pandas.core.arrays.string_ import StringDtype
+from pandas.core.arrays.string_ import (
+    BaseStringArray,
+    StringDtype,
+)
 from pandas.core.indexers import (
     check_array_indexer,
     validate_indices,
@@ -86,7 +89,7 @@ def _chk_pyarrow_available() -> None:
 # fallback for the ones that pyarrow doesn't yet support
 
 
-class ArrowStringArray(OpsMixin, ExtensionArray, ObjectStringArrayMixin):
+class ArrowStringArray(OpsMixin, BaseStringArray, ObjectStringArrayMixin):
     """
     Extension array for string data in a ``pyarrow.ChunkedArray``.
 

pandas/core/dtypes/cast.py

@@ -420,18 +420,14 @@ def maybe_cast_to_extension_array(
     -------
     ExtensionArray or obj
     """
-    from pandas.core.arrays.string_ import StringArray
-    from pandas.core.arrays.string_arrow import ArrowStringArray
+    from pandas.core.arrays.string_ import BaseStringArray
 
     assert isinstance(cls, type), f"must pass a type: {cls}"
     assertion_msg = f"must pass a subclass of ExtensionArray: {cls}"
     assert issubclass(cls, ABCExtensionArray), assertion_msg
 
     # Everything can be converted to StringArrays, but we may not want to convert
-    if (
-        issubclass(cls, (StringArray, ArrowStringArray))
-        and lib.infer_dtype(obj) != "string"
-    ):
+    if issubclass(cls, BaseStringArray) and lib.infer_dtype(obj) != "string":
         return obj
 
     try:

pandas/core/strings/object_array.py

@@ -173,8 +173,7 @@ def scalar_rep(x):
 
             return self._str_map(scalar_rep, dtype=str)
         else:
-            from pandas.core.arrays.string_ import StringArray
-            from pandas.core.arrays.string_arrow import ArrowStringArray
+            from pandas.core.arrays.string_ import BaseStringArray
 
             def rep(x, r):
                 if x is libmissing.NA:
@@ -186,7 +185,7 @@ def rep(x, r):
 
             repeats = np.asarray(repeats, dtype=object)
             result = libops.vec_binop(np.asarray(self), repeats, rep)
-            if isinstance(self, (StringArray, ArrowStringArray)):
+            if isinstance(self, BaseStringArray):
                 # Not going through map, so we have to do this here.
                 result = type(self)._from_sequence(result)
             return result